A fully-automated deep learning method for regional analysis of myocardial T2* closely matched expert manual segmentation with excellent intraclass correlation (ICC range 0.944-0.996).
Does a fully-automated deep learning method accurately segment and quantify myocardial T2* values compared to expert manual segmentation in patients with iron overload diseases?
A fully automated deep learning method provides fast and accurate regional analysis of myocardial T2* values for iron quantification, matching expert manual segmentation.
Estimación del efecto: ICC range 0.944-0.996
Cardiovascular magnetic resonance (CMR) T2* mapping is the gold standard technique for the assessment of iron overload in the heart. The quantitative analysis of T2* values requires the manual segmentation of T2* images, which is a time-consuming and operator-dependent procedure. This study describes a fully-automated method for the regional analysis of myocardial T2* distribution using a deep convolutional neural network (CNN). A CNN with U-Net architecture was trained to segment multi-echo T2*-weighted images in 16 sectors in accordance with the American Heart Association (AHA) model. We used images from 210 patients (three slices, 10 multi-echo images) with iron overload diseases to train and test the CNN. The performance of the proposed method was quantitatively evaluated on an independent holdout test set by comparing the segmentation accuracy of the CNN and the T2* values obtained by the automated method against ground-truth labels provided by two experts. Segmentation metrics and global and regional T2* values assessed by the proposed DL method closely matched those obtained by experts with excellent intraclass correlation in all myocardial sectors of the AHA model (ICC range 0.944, 0.996). This method could be effectively adopted in the clinical setting for fast and accurate analysis of myocardial T2*.
Martini et al. (Thu,) conducted a other in Iron overload diseases (n=210). Deep convolutional neural network (CNN) for automated regional analysis of myocardial T2* vs. Manual segmentation by experts was evaluated on Intraclass correlation of global and regional T2* values between CNN and experts (ICC range 0.944-0.996). A fully-automated deep learning method for regional analysis of myocardial T2* closely matched expert manual segmentation with excellent intraclass correlation (ICC range 0.944-0.996).